Mmcp.market

coldstart MCP server

by AkashGoenka·io.github.AkashGoenka/coldstart·v2.2.17
No reviews yet

Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

10 stars833 downloads/wk

Reviews

Write one

Nobody has reviewed coldstart yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

coldstart tools (8, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • find

    Locate the files relevant to a task. Pass `query` = EVERY salient identifier from the task (symbol names, domain nouns, the rare token you half-remember) — not one distilled keyword. Recall is bounded by the terms you give: a one-token query cannot out-rank lookalikes, so over-supply rather than under-supply. Reach for find BEFORE Read/Grep/Glob.

  • gs

    Drill into a known file. Returns these sections as compact text:

  • kb_lookup

    Read everything the NOTEBOOK knows at ONE exact address — the file you are about to edit. Address-keyed, not concept-keyed: unlike kb_search (fuzzy, ranked), this filters notes by exact anchor path, so it is exhaustive at that path. Returns the file note's facets, every cross-file flow that passes THROUGH this file, and lessons/absences anchored here — each with a live freshness stamp against the

  • kb_repair

    List the notebook notes that are WRITTEN BUT UNFINDABLE — missing the fields a note cannot be retrieved without (identityAliases, anchor symbols, a flow's verified paths). Notes written before those fields were required are correct but unreachable, and this is how they get found.

  • kb_repair_aliases

    List file/flow notes whose identityAliases may no longer describe them — a DIFFERENT problem from kb_repair: that one finds notes with NO aliases at all, this one is for aliases that exist but have gone stale (a note rewritten several times can carry words that were really symptoms of an earlier write, not stable facts). Paginated 10 notes at a time.

  • kb_search

    Search the repo's NOTEBOOK — durable notes past agents wrote after finishing tasks here (file purposes, cross-file flows, traps/lessons, established absences). Try this BEFORE find when the task might have been seen before: a hit can answer outright or point straight at the right files, skipping a search. Pass plain task words (symptoms work: "logout loop after refresh"), symbol names, or file nam

  • kb_status

    Notebook overview: how many notes exist (by type: file/flow/lesson), how many are flagged stale (their anchored files drifted since verification), and how many are superseded/retracted. Pass `paths` (array of repo-relative paths) to instead list the notes anchored at each of those exact paths with their freshness state — a quick "is anything known here?" check across several files at once.

  • kb_writewrite action

    Save or correct NOTEBOOK notes after finishing real work here — you have the files in context, so no future agent is better placed to record what you learned. Write a file note (what a file is for), a flow note (how a task spans files), or an absence lesson (a confirmed "there is no X"). Pass `specs` (an ARRAY of specs) to write ALL your notes in ONE call — malformed notes are reported together in

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scan212 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the coldstart repository's README, as published. We do not edit it. Read it on GitHub

coldstart

Self-maintaining codebase knowledge for AI coding agents. Agent-written notes that stay anchored to your code — plus fast, deterministic navigation — so Claude Code, Codex, and Cursor stop rediscovering the repo every session.

Website  ·  Docs  ·  Blog  ·  Philosophy  ·  npm

Two layers, one tool:

  • The notebook (coldstart kb) — durable, agent-written notes about how this codebase actually works: what a file is for, how a flow spans files, which invariants hold. Captured after real tasks, recalled when a later task matches, and kept honest by the index — every note is anchored to real files, and a note whose evidence drifted is flagged, not served as truth.
  • Navigation (coldstart find / coldstart gs) — a fast static index over file paths, symbol names, exports, and the import/call graph. It answers "which files are relevant to this task?" in milliseconds, with checkable evidence instead of a similarity score.

No embeddings, no model to run, no service to babysit. Agents are already good at reading and reasoning about code; what they waste tokens on is finding the right file and re-deriving what the last session already figured out. coldstart does those two parts and gets out of the way.

Install

Requires Node.js 18+.

npm install -g @cstart/coldstart
cd your-project
coldstart init   # coldstart.md + client wiring + notebook + background index warm-up

A single coldstart init does everything — navigation and the notebook. It asks two things — the experience (cli, recommended, or mcp) and the client — then writes the agent-facing guidance into the client's own rules file (as an imported coldstart.md for Claude Code; inlined directly for Cursor and Codex, which don't resolve @file references), wires the client, and sets up the notebook (skeleton, git wiring, and — for Claude Code, Codex, and Cursor — the capture/recall hooks). Pass --experience / --client to skip the prompts. The client is never auto-detected; you always pick it.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y @cstart/coldstart on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add coldstart -- npx -y @cstart/coldstart
Add to Cursor

coldstart: common questions

Is coldstart MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the coldstart safety report
How do I install coldstart?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does coldstart need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is coldstart maintained?
The last commit was 5 days ago (2026-09-19). The latest release is v2.2.17.
What can I use instead of coldstart?
Servers from other publishers that do the same job: IWE MCP server, Basic Memory MCP server and Agent-Native Clips MCP server. Compare all coldstart alternatives.

Alternatives to coldstart

Same job from other publishers: the closest match first, then the best rated.

All coldstart alternatives →
  • IWE
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    C
  • Agent-Native Clips
    Screen recording, meeting notes, and voice dictation - all with AI
    A
  • ContextStream MCP Server
    Project memory, semantic code search, and grounded agent context.
    A
  • Mnemoverse Memory
    Hosted AI agent memory that learns from outcomes, with shared rooms, in Claude, Cursor and ChatGPT.
    A
coldstart vs IWEcoldstart vs Basic Memorycoldstart vs Agent-Native Clips

More from AkashGoenka →